[Model Runner V2] Support FLASHINFER_MLA backend (#32709)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2026-01-20 10:26:17 -08:00
committed by GitHub
parent 04a9e064db
commit 9ab4388cd3
2 changed files with 2 additions and 2 deletions
+1 -1
View File
@@ -248,7 +248,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
)
# TODO(woosuk): Support other backends.
supported_backends = ("FLASH_ATTN", "FLASHINFER")
supported_backends = ("FLASH_ATTN", "FLASHINFER", "FLASHINFER_MLA")
for backend in self.attn_backends.values():
backend_name = backend.get_name()
if backend_name not in supported_backends: